Seizure Detection

The CHB-MIT dataset is a dataset of EEG recordings from pediatric subjects with intractable seizures. Subjects were monitored for up to several days following withdrawal of anti-seizure mediation in order to characterize their seizures and assess their candidacy for surgical intervention. The dataset contains 23 patients divided among 24 cases (a patient has 2 recordings, 1.5 years apart). The dataset consists of 969 Hours of scalp EEG recordings with 173 seizures. There exist various types of seizures in the dataset (clonic, atonic, tonic). The diversity of patients (Male, Female, 10-22 years old) and different types of seizures contained in the datasets are ideal for assessing the performance of automatic seizure detection methods in realistic settings. Source: Learning Robust Features using Deep Learning for Automatic Seizure Detection Image Source: https://archive.physionet.org/pn6/chbmit/

Our goal is to enable deep learning research in neuroscience by releasing the largest publicly available unencumbered database of EEG recordings. This ongoing project currently includes over 30,000 EEGs spanning the years from 2002 to present. Data collected can be used for both research and commercialization purposes. Iyad Obeid and Joseph Picone. The temple university hospital eeg data corpus. Frontiers in neuroscience,10:196, 2016.

Neonatal seizures are a common emergency in the neonatal intensive care unit (NICU). There are many questions yet to be answered regarding the temporal/spatial characteristics of seizures from different pathologies, response to medication, effects on neurodevelopment and optimal detection. This dataset contains EEG recordings from human neonates and the visual interpretation of the EEG by the human expert. Multi-channel EEG was recorded from 79 term neonates admitted to the neonatal intensive care unit (NICU) at the Helsinki University Hospital. The median recording duration was 74 minutes (IQR: 64 to 96 minutes). EEGs were annotated by three experts for the presence of seizures. An average of 460 seizures were annotated per expert in the dataset, 39 neonates had seizures by consensus and 22 were seizure free by consensus. The dataset can be used as a reference set of neonatal seizures, for the development of automated methods of seizure detection and other EEG analysis, as well as for the analysis of inter-observer agreement.

This dataset is a BIDS-compatible version of the CHB-MIT Scalp EEG Database. It reorganizes the file structure to comply with the BIDS specification. To this effect: The data from subject chb21 was moved to sub-01/ses-02. Metadata was organized according to BIDS. Data in the EEG edf files was modified to keep only the 18 channels from a double banana bipolar montage. Annotations were formatted as BIDS-score compatible tsv files.

This dataset is a BIDS compatible version of the Siena Scalp EEG Database. It reorganizes the file structure to comply with the BIDS specification. To this effect: Metadata was organized according to BIDS. Data in the EEG edf files was modified to keep only the 19 channels from a 10-20 EEG system. Annotations were formatted as BIDS-score compatible tsv files.

This dataset is obtained during an ICON project (2017-2018) in collaboration with KU Leuven (ESAT-STADIUS), UZ Leuven, UCB, Byteflies and Pilipili. The goal of this project was to design a system using Behind the ear (bhE) EEG electrodes for monitoring the patient in a home environment. This way, a nice balance can be found between sufficient accuracy of seizure detection algorithms (because EEG is used) and wearability (bhe EEG is relatively subtle, similar to a hear-aid device). The dataset acquired in the hospital during presurgical evaluation. During such presurgical evaluation, neurologists try to see if a specific part of the brain is causing the seizures, and if so, if that part of the brain can be removed during surgery. During the presurgical evaluation, patients are monitored using the vEEG for multiple days (typically a week). Patients are however restricted to move within their room because of the wiring and video analysis. In this dataset, following data is available per patient: • Full 10-20 scalp EEG data of the patient during the presurgical evaluation. • Behind-the-ear data (2 sensors positioned behind each ear) • Single-lead ECG data (typically lead II) Seizures are annotated by the clinicians based on the gold standard vEEG system. These seizure annotations are also available in the dataset. In total 82 patients were recorded between 23/01/2017 and 26/10/2018. From those patients, 54 were recorded with the bhe channels. Forty-two of those patients had seizures during their presurgical evaluation, while for twelve patients no seizure has been recorded. The number of seizures per patient ranged from 1 to 22, with a median of 3 seizures per patient. The duration of the seizures, the time difference of seizure EEG onset and end, varied between 11 and 695 seconds with a median of 50 seconds. 89% of the seizures were Focal Impaired Awareness seizures. 91% of the seizures originated from the (fronto-) temporal lobe. In the folder ’Data’ the raw data in the form of .edf, are provided with annotations for all the patients. The annotations are provided in .tsv (tab separated values) files. For every seizure the first column represents the starting point (in seconds) of the seizure, the second one the end point of the seizure, the third one the type of the seizure, while in the last column extra information are provided. The extra information includes the origin of the seizure, the hemisphere and if the seizure can be noted from the behind the ear channels (bhe:1 in that case). In the header section of every file information concerning the dataset and the annotations used are included. For every subject and for every session (even if no seizure is present) two different sets of annotations are provided. The ”a1”set of annotations is the annotations as provided by the doctors. The ”a2” set of annotations are the annotations used in [2] for training of the algorithm. The annotations provided from the doctors were not always perfectly aligned with the typical rhythmic ictal pattern, hence in ”a2” a refinement of the start of each annotation was performed visually by an engineer. Furthermore, in the annotations of the doctor the end point of some seizures was missing (”none”) in the ”a2” subset of annotations each seizure was considered with a stable length of 10 seconds.

The database consists of EEG recordings of 14 patients acquired at the Unit of Neurology and Neurophysiology of the University of Siena. Subjects include 9 males (ages 25-71) and 5 females (ages 20-58). Subjects were monitored with a Video-EEG with a sampling rate of 512 Hz, with electrodes arranged on the basis of the international 10-20 System. Most of the recordings also contain 1 or 2 EKG signals. The diagnosis of epilepsy and the classification of seizures according to the criteria of the International League Against Epilepsy were performed by an expert clinician after a careful review of the clinical and electrophysiological data of each patient.

Seizures and seizure-like rhythmic and periodic brain activity known as “ictal-interictal-injury continuum” (IIIC) patterns are frequently detected during brain monitoring with electroencephalography (EEG) in patients with epilepsy or critical illness. Prior efforts to automate detection of IIIC patterns have been limited by lack of large well-annotated datasets to train/evaluate algorithms, and there have been only a few attempts to detect IIIC events other than seizures. The IIIC dataset includes 50,697 labeled EEG samples from 2,711 patients’ and 6,095 EEGs that were annotated by physician experts from 18 institutions. These samples were used to train SPaRCNet (Seizures, Periodic and Rhythmic Continuum patterns Deep Neural Network), a computer program that classifies IIIC events with an accuracy matching clinical experts. Prior efforts to automate seizure detection have been limited by lack of large well-annotated datasets to train and evaluate algorithms, and there have been only a few attempts to detect IIIC events other than seizures. To address this gap, we created a set of 50,697 IIIC and non-IIIC events from 2,711 patients’ (6,095 EEGs) and obtained independent annotations from 124 raters